I am trying to experiment with SphinxTrain. I was wondering if it is possible
to extend or adapt an existing acoustic model such as WSJ as well as creating
a new one from scratch for a given domain. I would like to do this and then
compare the performance of each model.
Thanks
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello,
I am trying to experiment with SphinxTrain. I was wondering if it is possible
to extend or adapt an existing acoustic model such as WSJ as well as creating
a new one from scratch for a given domain. I would like to do this and then
compare the performance of each model.
Thanks
See the page on the wiki
http://cmusphinx.sourceforge.net/wiki/acousticmodeladaptation